Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

...

Browse Source
This commit is contained in:
Kovid Goyal 2010-10-31 21:00:38 -06:00
parent bdf2cd48dd
commit 21731b3c04
1 changed files with 6 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
src/calibre/utils/html2text.py
View File

@ -9,7 +9,7 @@ __contributors__ = ["Martin 'Joey' Schulze", "Ricardo Reyes", "Kevin Jay North"]
# Support decoded entities with unifiable. # Support decoded entities with unifiable.
if not hasattr(__builtins__, 'True'): True, False = 1, 0 if not hasattr(__builtins__, 'True'): True, False = 1, 0
import re, sys, urllib, htmlentitydefs, codecs, StringIO, types import re, sys, urllib, htmlentitydefs, codecs
import sgmllib import sgmllib
import urlparse import urlparse
sgmllib.charref = re.compile('&#([xX]?[0-9a-fA-F]+)[^0-9a-fA-F]') sgmllib.charref = re.compile('&#([xX]?[0-9a-fA-F]+)[^0-9a-fA-F]')
@ -18,17 +18,17 @@ try: from textwrap import wrap
except: pass except: pass
# Use Unicode characters instead of their ascii psuedo-replacements # Use Unicode characters instead of their ascii psuedo-replacements
UNICODE_SNOB = 0 UNICODE_SNOB = 1
# Put the links after each paragraph instead of at the end. # Put the links after each paragraph instead of at the end.
LINKS_EACH_PARAGRAPH = 0 LINKS_EACH_PARAGRAPH = 0
# Wrap long lines at position. 0 for no wrapping. (Requires Python 2.3.) # Wrap long lines at position. 0 for no wrapping. (Requires Python 2.3.)
BODY_WIDTH = 78 BODY_WIDTH = 0
# Don't show internal links (href="#local-anchor") -- corresponding link targets # Don't show internal links (href="#local-anchor") -- corresponding link targets
# won't be visible in the plain text file anyway. # won't be visible in the plain text file anyway.
SKIP_INTERNAL_LINKS = False SKIP_INTERNAL_LINKS = True
### Entity Nonsense ### ### Entity Nonsense ###
@ -433,6 +433,7 @@ if __name__ == "__main__":
j = urllib.urlopen(baseurl) j = urllib.urlopen(baseurl)
try: try:
from feedparser import _getCharacterEncoding as enc from feedparser import _getCharacterEncoding as enc
enc
except ImportError: except ImportError:
enc = lambda x, y: ('utf-8', 1) enc = lambda x, y: ('utf-8', 1)
text = j.read() text = j.read()